Theros/Qwen2.5-CyberMix-7B
Full fine-tune vs bunnycore/Qevacot-7B-v2. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196
3 derivatives checked
- mradermacher/Qwen2.5-CyberMix-7B-i1-GGUF: Quantization
- mradermacher/Qwen2.5-CyberMix-7B-GGUF: Same weights, converted
- SvalTek/Qwen2.5-ColdBrew: LoRA-style